Content-based retrieval allows finding information by
searching its content rather than its attributes. The challenge
facing content-based video retrieval (CBVR) is to design
systems that can accurately and automatically process large
amounts of heterogeneous videos. Moreover, content-based
video retrieval system requires in its first stage to segment the
video stream into separate shots. Afterwards features are
extracted for video shots representation. And finally, choose a
similarity/distance metric and an algorithm that is efficient
enough to retrieve query – related videos results. There are two
main issues in this process; the first is how to determine the best
way for video segmentation and key frame selection. The
second is the features used for video representation. Various
features can be extracted for this sake including either low or
high level features. A key issue is how to bridge the gap between
low and high level features. This paper proposes a system for a
content based video retrieval system that tries to address the
aforementioned issues by using adaptive threshold for video
segmentation and key frame selection as well as using both low
level features together with high level semantic object
annotation for video representation. Experimental results show
that the use of multi features increases both precision and recall rates by about 13% to 19 % than traditional system that uses only color feature for video retrieval |
